Method and apparatus for adaptively constructing three-dimensional indoor scenario

1. A method for adaptively constructing a three-dimensional indoor scenario, comprising: establishing an object association map corresponding to different scenario categories according to an annotated indoor layout; selecting a corresponding target indoor object according to room information inputted by a user and the object association map, wherein the room information comprises a room type and a designated indoor object; generating a target indoor layout according to preset room parameters inputted by the user and the annotated indoor layout, wherein the preset room parameters comprise a room type parameter and a plot ratio parameter, the plot ratio parameter refers to a ratio of a total area of all indoor objects to an area of a room; and constructing a three-dimensional indoor scenario according to the target indoor object and the target indoor layout; wherein the selecting a corresponding target indoor object according to room information inputted by a user and the object association map comprises: determining a scenario category of a room according to the room information inputted by the user; determining the object association map corresponding to the scenario category according to the scenario category; and selecting the corresponding target indoor object according to the object association map; wherein the determining a scenario category of a room according to the room information inputted by the user comprises: arg ⁢ ⁢ min S ~ ⁢  θ r - ∑ S ~ ⁢ θ ~ r s i  θ r determining the scenario category of the room according to max s i ∈ S ~ ⁢ P ⁡ ( o j | s i ) > 0 ⁢ ⁢ and ⁢ ⁢ ∑ s i ∈ S ~ ⁢ N ⁡ ( o j , s i ) ≥ n o j , ∀ o j ∈ O ~ , satisfying wherein θ r is an ∑ S ~ ⁢ θ ~ r s i area of a room associated with the inputted room information, is the average area of all scenario categories in the scenario category set S % ; P(o j |s i ) is the probability that the indoor object o j be included in the scenario category s i ; N(o j ,s i ) is the maximum number of o j existing in a single planar layout among all planar layouts of s i , and n o j is the number of indoor objects in a user-designated object category set {o j }.

2. The method according to claim 1 , wherein the establishing an object association map corresponding to different scenario categories according to an annotated indoor layout comprises: prefetching the annotated indoor layout; determining an association weight corresponding to each indoor object according to the annotated indoor layout; and establishing the object association map corresponding to different scenario categories according to the association weight.

3. The method according to claim 1 , wherein the generating a target indoor layout according to preset room parameters inputted by the user and the annotated indoor layout comprises: selecting at least two intermediate indoor layouts among the annotated indoor layout according to the room parameter; and applying a weighted combination to the at least two intermediate indoor layouts to generate the target indoor layout.

4. An apparatus for adaptively constructing a three-dimensional indoor scenario, comprising a processor, wherein the processor is configured to: establish an object association map corresponding to different scenario categories according to an annotated indoor layout; select a corresponding target indoor object according to room information inputted by a user and the object association map, wherein the room information comprises a room type and a designated indoor object; generate a target indoor layout according to preset room parameters inputted by the user and the annotated indoor layout, wherein the preset room parameters comprise a room type parameter and a plot ratio parameter, the plot ratio parameter refers to a ratio of a total area of all indoor objects to an area of a room; and construct a three-dimensional indoor scenario according to the target indoor object and the target indoor layout; wherein the processor is further configured to: determine a scenario category of a room according to the room information inputted by the user; determine an object association map corresponding to the scenario category according to the scenario category; and select the corresponding target indoor object according to the object association map; arg ⁢ ⁢ min S ~ ⁢  θ r - ∑ S ~ ⁢ θ ~ r s i  θ r , determine a room scenario category according to max s i ∈ S ~ ⁢ P ⁡ ( o j | s i ) > 0 ⁢ ⁢ and ⁢ ⁢ ∑ s i ∈ S ~ ⁢ N ⁡ ( o j , s i ) ≥ n o j , ∀ o j ∈ O ~ , satisfying wherein θ r is an ∑ S ~ ⁢ θ ~ r s i area of a room associated with the inputted room information, is the average area of all scenario categories in the scenario category set S % ; P(o j |s i ) is the probability that the indoor object o j be included in the scenario category s i ; N(o j ,s i ) is the maximum number of o j existing in a single planar layout among all planar layouts of s i , and n o j is the number of indoor objects in a user-designated object category set {o j }.

5. The apparatus according to claim 4 , wherein the processor is further configured to: the establishing unit is configured to: prefetch the annotated indoor layout; determine an association weight corresponding to each indoor object according to the annotated indoor layout; and establish the object association map corresponding to different scenario categories according to the association weight.

6. The apparatus according to claim 4 , wherein the processor is further configured to: select at least two intermediate indoor layouts among the annotated indoor layout according to the room parameter; and apply a weighted combination to the at least two intermediate indoor layouts to generate the target indoor layout.